From: Remita Amine Date: Sun, 2 Apr 2017 08:22:09 +0000 (+0100) Subject: [discoveryvr] Add new extractor(closes #12578) X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=a9bb61a4259972378dec5ef45d181fec150146b8;p=youtube-dl [discoveryvr] Add new extractor(closes #12578) --- diff --git a/youtube_dl/extractor/discoveryvr.py b/youtube_dl/extractor/discoveryvr.py new file mode 100644 index 000000000..cb63c2649 --- /dev/null +++ b/youtube_dl/extractor/discoveryvr.py @@ -0,0 +1,59 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import parse_duration + + +class DiscoveryVRIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?discoveryvr\.com/watch/(?P[^/?#]+)' + _TEST = { + 'url': 'http://www.discoveryvr.com/watch/discovery-vr-an-introduction', + 'md5': '32b1929798c464a54356378b7912eca4', + 'info_dict': { + 'id': 'discovery-vr-an-introduction', + 'ext': 'mp4', + 'title': 'Discovery VR - An Introduction', + 'description': 'md5:80d418a10efb8899d9403e61d8790f06', + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + bootstrap_data = self._search_regex( + r'root\.DVR\.bootstrapData\s+=\s+"({.+?})";', + webpage, 'bootstrap data') + bootstrap_data = self._parse_json( + bootstrap_data.encode('utf-8').decode('unicode_escape'), + display_id) + videos = self._parse_json(bootstrap_data['videos'], display_id)['allVideos'] + video_data = next(video for video in videos if video.get('slug') == display_id) + + series = video_data.get('showTitle') + title = episode = video_data.get('title') or series + if series and series != title: + title = '%s - %s' % (series, title) + + formats = [] + for f, format_id in (('cdnUriM3U8', 'mobi'), ('webVideoUrlSd', 'sd'), ('webVideoUrlHd', 'hd')): + f_url = video_data.get(f) + if not f_url: + continue + formats.append({ + 'format_id': format_id, + 'url': f_url, + }) + + return { + 'id': display_id, + 'display_id': display_id, + 'title': title, + 'description': video_data.get('description'), + 'thumbnail': video_data.get('thumbnail'), + 'duration': parse_duration(video_data.get('runTime')), + 'formats': formats, + 'episode': episode, + 'series': series, + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 46e5e3a1d..13ca1d2cd 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -273,6 +273,7 @@ from .discoverygo import ( DiscoveryGoPlaylistIE, ) from .discoverynetworks import DiscoveryNetworksDeIE +from .discoveryvr import DiscoveryVRIE from .disney import DisneyIE from .dispeak import DigitallySpeakingIE from .dropbox import DropboxIE